A Multimodal Authentication for Biometric Recognition System using Intelligent Hybrid Fusion Techniques

Biometric Recognition and Authentication is used in many applications for the secured identification of the persons. Several Researches has been carried out to strengthen the security algorithms through which the identification can be done in secured manner. With this objective, a new algorithm called Hybrid Adaptive Fusion(HAF) has been proposed which works on the principle of hybrid fusion of two feature inputs such as Hand geometry and iris of the users. As mentioned, the proposed algorithm uses the novel and hybrid fusion of feature extraction along with the accurate machine learning classifier. Effective Linear Binary Patterns (ELBP) and Scale Invariant Fourier Transform (SIFT) are stored in the databases for the further verification. The features stored are fed into the Extreme Learning machines for the detection of the verified users. This algorithm has been tested with the CASIA Image Datasets and with the different classifiers such as Neural Networks, Baiyes Networks. The proposed algorithm with ELM has better accuracy of 98.5% when compared with the other machine learning algorithms.